key4hep / key4hep/k4MLJetTagger

Improve primary vertex fit -> improve jet tagger

Open
#7 0 comments 0 reactions 0 assignees View on GitHub
Dominant language
Jupyter Notebook
Stars
1
Forks
5
PR merge metrics
No merged PRs in 30d

Description

[Primary_Vertex_Fitting.pdf](https://github.com/user-attachments/files/19910480/Primary_Vertex_Fitting.pdf)
Once the PV fit issue (see https://github.com/key4hep/CLDConfig/issues/61) is fixed, retrain the model. It will most likely improve the performance especially for light tagging or against-light tagging.

Documentation on the issue attached as a pdf.

Contributor guide

Open the contributing guide

Research direction

Start by reading the attached Primary_Vertex_Fitting.pdf and the linked CLDConfig issue #61 to understand the prerequisite primary-vertex fit change. Then locate the model training entry point in k4MLJetTagger and determine how retraining is performed. Done means retraining after the PV fix and evaluating whether light-tagging or against-light-tagging performance improves.

Written by the indexing model from the issue text.

Assessment

Tech stack
jupyter-notebook, machine-learning
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.